arXiv cs.MA· Zhonghang Li, Zongwei Li, Chao Huang·· 12 小时前AI 评分40
AutoSwarm：自动化智能体集群的多智能体框架
AutoSwarm: Automating Agent Swarms
AI 导读
AutoSwarm 是一个面向协作问题求解的多智能体框架，通过协作形成机制联合定义责任边界与验收条件，并用共享状态耦合各智能体的局部进展以协调执行。在长程编程、交互式规划和专业金融分析实验中，AutoSwarm 表现优于单智能体基线和现有多智能体框架，源代码已公开。
正文
Abstract:Large language model (LLM) agents increasingly automate complex tasks, with multi-agent systems seeking further performance gains through specialization and collaboration. However, distributing work across agents does not automatically yield complementary contributions, and inter-agent dependencies can turn local errors into task failure. To address these challenges, we propose AutoSwarm, a multi-agent framework for collaborative problem solving. Collaboration formation jointly defines responsibility boundaries and conditions for acceptance and downstream use, grounding capability allocation in contributions that other agents can assess and integrate toward a shared objective. Execution coordination couples agents' local progress through a shared state, using dependencies and supervisory relationships to govern agent activation, result handoffs, and integration while adapting subsequent actions to review feedback and emerging blockers. Experiments spanning long-horizon programming, interactive planning, and professional financial analysis demonstrate AutoSwarm's advantages over single-agent baselines and existing multi-agent frameworks. Source code is available at this https URL.
| Subjects: | Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.33048 [cs.MA] |
| (or arXiv:2610.33048v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33048 arXiv-issued DOI via DataCite |
Submission history
From: Zhonghang Li [view email]
[v1]
Sat, 17 Oct 2026 08:45:11 UTC (320 KB)
来源：arXiv cs.MA · arxiv.org